Triple
T25996519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Air Force Benevolent Fund |
E646500
|
entity |
| Predicate | charityCategory |
P159646
|
FINISHED |
| Object | welfare charity |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: welfare charity | Statement: [Royal Air Force Benevolent Fund, charityCategory, welfare charity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: charityCategory Context triple: [Royal Air Force Benevolent Fund, charityCategory, welfare charity]
-
A.
charityCategory
chosen
Indicates the specific type or classification of charitable activity or purpose associated with an entity.
-
B.
associatedCharity
Indicates that one entity has a formal or recognized charitable affiliation or partnership with another entity.
-
C.
charitySinglePurpose
Indicates that a charity is established and operated for a single, specific charitable purpose rather than multiple distinct purposes.
-
D.
charityComponent
Indicates that one entity functions as a charitable element, feature, or part within another entity or larger arrangement.
-
E.
philanthropicDonation
Indicates that one entity voluntarily gives money, goods, or services to another entity for charitable or public-benefit purposes without expecting direct compensation.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e77e88cb8481908da31d4a00661f55 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6056f481c81909fd23b04483b76a0 |
completed | May 2, 2026, 2:08 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 8:58 a.m.